POS Tagging Using Relaxation Labelling

Relaxation labelling is an optimization technique used in many fields to solve contraint satisfcation problems. The algorithm finds a combination of values for a set of variables such that satisfies -to the maximum possible degree- a set of given constraints. This paper describes some experiments performed applying it to POS tagging, and the results obtained. It also ponders the possibility of applying it to Word Sense Disambiguation.

[1]  Steven W. Zucker,et al.  Continuous Relaxation and Local Maxima Selection: Conditions for Equivalence , 1979, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Thomas M. Cover,et al.  Elements of Information Theory , 2005 .

[3]  Eric Brill,et al.  A Simple Rule-Based Part of Speech Tagger , 1992, HLT.

[4]  Carme Torras.  Relaxation and Neural Learning: Points of Convergence and Divergence , 1989, J. Parallel Distributed Comput..

[5]  Helmut Schmid,et al.  Part-of-Speech Tagging With Neural Networks , 1994, COLING.

[6]  Penelope Sibun,et al.  A Practical Part-of-Speech Tagger , 1992, ANLP.

[7]  David Elworthy,et al.  Does Baum-Welch Re-estimation Help Taggers? , 1994, ANLP.

[8]  Lluís Màrquez i Villodre,et al.  Towards learning a constraint grammar from annotated corpora using decision trees , 1996 .

[9]  P. Swain,et al.  On the accuracy of pixel relaxation labeling , 1981 .

[10]  Graeme Hirst,et al.  Semantic Interpretation and the Resolution of Ambiguity , 1987, Studies in natural language processing.

[11]  P. Resnik.  Selection and information: a class-based approach to lexical relationships , 1993 .

[12]  Van Nostrand,et al.  Error Bounds for Convolutional Codes and an Asymptotically Optimum Decoding Algorithm , 1967 .

[13]  German Rigau Claramunt.  An Experiment on automatic semantic tagging of dictionary senses , 1995 .

[14]  Emile H. L. Aarts,et al.  Boltzmann Machines and their Applications , 1987, PARLE.

[15]  George A. Miller,et al.  A Semantic Concordance , 1993, HLT.

[16]  S. A. Lloyd.  An optimization approach to relaxation labelling algorithms , 1983, Image Vis. Comput..

[17]  Marcello Pelillo,et al.  Learning Compatibility Coefficients for Relaxation Labeling Processes , 1994, IEEE Trans. Pattern Anal. Mach. Intell..